Update app.py

app.py

@@ -3,8 +3,8 @@ from transformers import pipeline
 import yt_dlp
 import whisper
 import os
-import uuid
 import re
+from urllib.parse import urlparse
 
 # Delete temporary files
 def clean_temp_files():
@@ -13,39 +13,56 @@ def clean_temp_files():
         if os.path.exists(file):
             os.remove(file)
 
-# Download YouTube video
+# Download YouTube video with improved options
 def download_video(video_url):
     try:
         ydl_opts = {
-            'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]',
-            'outtmpl': 'temp_video.mp4',
+            'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best',
+            'outtmpl': 'temp_video.%(ext)s',
             'quiet': True,
             'no_warnings': True,
+            'merge_output_format': 'mp4',
+            'retries': 3,
+            'socket_timeout': 30,
+            'extract_flat': False,
         }
         
         with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-            ydl.download([video_url])
-        return "temp_video.mp4"
+            info = ydl.extract_info(video_url, download=True)
+            filename = ydl.prepare_filename(info)
+            return filename if os.path.exists(filename) else None
+            
     except Exception as e:
-        print(f"Download error: {e}")
+        print(f"Download error: {str(e)}")
         return None
 
-# Extract audio (temporary)
+# Extract audio with better error handling
 def extract_audio(video_path):
-    os.system(f"ffmpeg -i \"{video_path}\" -vn -acodec libmp3lame -q:a 3 \"temp_audio.mp3\" -y")
-    return "temp_audio.mp3" if os.path.exists("temp_audio.mp3") else None
+    try:
+        if not os.path.exists(video_path):
+            return None
+            
+        audio_path = "temp_audio.mp3"
+        os.system(f"ffmpeg -i \"{video_path}\" -vn -acodec libmp3lame -q:a 2 \"{audio_path}\" -y -loglevel error")
+        return audio_path if os.path.exists(audio_path) else None
+    except Exception as e:
+        print(f"Audio extraction error: {str(e)}")
+        return None
 
-# Transcribe audio
+# Transcribe audio with model caching
 def transcribe_audio(audio_path):
     try:
+        if not os.path.exists(audio_path):
+            return None
+            
         model = whisper.load_model("base")
-        result = model.transcribe(audio_path)
+        result = model.transcribe(audio_path, fp16=False)  # fp16=False for better compatibility
         return result['text']
     except Exception as e:
-        print(f"Transcription error: {e}")
+        print(f"Transcription error: {str(e)}")
         return None
 
-# Classify content
+# Classify content with fallback
 def classify_content(text):
     try:
         if not text or len(text.strip()) == 0:
@@ -63,48 +80,66 @@ def classify_content(text):
         
         return result['labels'][0], result['scores'][0]
     except Exception as e:
-        print(f"Classification error: {e}")
+        print(f"Classification error: {str(e)}")
         return None, None
 
-# Main processing function
+# Validate YouTube URL
+def is_valid_youtube_url(url):
+    youtube_domains = ['youtube.com', 'www.youtube.com', 'youtu.be', 'www.youtu.be']
+    try:
+        parsed = urlparse(url)
+        if not parsed.scheme in ('http', 'https'):
+            return False
+        if not any(domain in parsed.netloc for domain in youtube_domains):
+            return False
+        return True
+    except:
+        return False
+
+# Main processing function with better error handling
 def process_video(video_url):
     clean_temp_files()
     
     if not video_url or len(video_url.strip()) == 0:
         return "Please enter a valid YouTube URL", ""
     
-    if "youtube.com" not in video_url and "youtu.be" not in video_url:
-        return "Please enter a valid YouTube URL", ""
-    
-    # Download video
-    video_path = download_video(video_url)
-    if not video_path:
-        return "Failed to download video", ""
-    
-    # Extract audio
-    audio_path = extract_audio(video_path)
-    if not audio_path:
-        clean_temp_files()
-        return "Failed to extract audio", ""
+    if not is_valid_youtube_url(video_url):
+        return "Please enter a valid YouTube URL (should start with https://youtube.com or https://youtu.be)", ""
     
-    # Transcribe
-    transcription = transcribe_audio(audio_path)
-    if not transcription:
+    try:
+        # Download video
+        video_path = download_video(video_url)
+        if not video_path:
+            return "Failed to download video (may be private, age-restricted, or unavailable)", ""
+        
+        # Extract audio
+        audio_path = extract_audio(video_path)
+        if not audio_path:
+            clean_temp_files()
+            return "Failed to extract audio from video", ""
+        
+        # Transcribe
+        transcription = transcribe_audio(audio_path)
+        if not transcription:
+            clean_temp_files()
+            return "Failed to transcribe audio (may be no speech detected)", ""
+        
+        # Classify
+        category, confidence = classify_content(transcription)
+        if not category:
+            clean_temp_files()
+            return transcription, "Failed to classify content"
+        
+        # Clean up
         clean_temp_files()
-        return "Failed to transcribe audio", ""
-    
-    # Classify
-    category, confidence = classify_content(transcription)
-    if not category:
+        
+        # Format classification result
+        classification_result = f"{category} (confidence: {confidence:.2f})"
+        return transcription, classification_result
+        
+    except Exception as e:
         clean_temp_files()
-        return transcription, "Failed to classify content"
-    
-    # Clean up
-    clean_temp_files()
-    
-    # Format classification result
-    classification_result = f"{category} (confidence: {confidence:.2f})"
-    return transcription, classification_result
+        return f"An error occurred: {str(e)}", ""
 
 # Gradio interface
 with gr.Blocks(title="YouTube Content Analyzer") as demo:
@@ -116,7 +151,8 @@ with gr.Blocks(title="YouTube Content Analyzer") as demo:
     with gr.Row():
         url_input = gr.Textbox(
             label="YouTube URL",
-            placeholder="Enter YouTube video URL here..."
+            placeholder="Enter YouTube video URL here...",
+            max_lines=1
         )
     
     with gr.Row():
@@ -138,8 +174,8 @@ with gr.Blocks(title="YouTube Content Analyzer") as demo:
     # Examples
     gr.Examples(
         examples=[
-            ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"],
-            ["https://youtu.be/dQw4w9WgXcQ"]
+            ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"],  # Rick Astley - Never Gonna Give You Up
+            ["https://youtu.be/J---aiyznGQ"]  # Keyboard Cat
         ],
         inputs=url_input
     )